test-reporting-triage-skill

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes runtime data such as error messages and stack traces, which are then interpolated into Slack messages and GitHub Issues. This creates a surface for indirect prompt injection if test outputs can be influenced by untrusted external inputs.
  • Ingestion points: The categorize method in FailureAnalyzer (SKILL.md) reads error.message and error.stack.
  • Boundary markers: The generateReport and generateSlackMessage methods (SKILL.md) wrap error content in Markdown code blocks.
  • Capability inventory: The GitHub workflow (SKILL.md) utilizes Slack and GitHub APIs to post the generated content.
  • Sanitization: The skill does not perform explicit sanitization or filtering of the error messages before including them in the final output.
  • [EXTERNAL_DOWNLOADS]: The CI integration logic includes well-known and official GitHub Actions from the actions and slackapi organizations for repository checkout, artifact handling, and Slack notifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:31 AM
Security Audit — agent-trust-hub — test-reporting-triage-skill